PIVOT - Iterative Visual Prompting Elicits Actionable Knowledge for VLMs

ai
Author

Seil Kang

Published

April 12, 2024

이 글은 S. Nasiriany et al. (Google DeepMind) 이 arXiv.2402에 게재한 PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs를 읽고 정리한 글입니다.

TO BE UPDATED

Grounding VLMs to Robot Actions through Image Annotations

3D to 2D Camera Calibration [link]

Prompting with Iterative Visual Optimization

Reuse